Research map / Large language models / Retrieval and knowledge
Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts
Ruth Dannenfelser, Jeffrey Zhong, Ran Zhang, Vicky Yao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train on FlaMBe tool annotations instead of Softcite | PubMedBERT tool NER · FlaMBe held-out 11 papers | F1: 0.453 -> 0.839 | Improved |
| train on FlaMBe tool annotations instead of Softcite | PubMedBERT tool NER · FlaMBe held-out 11 papers | precision: 0.397 -> 0.779 | Improved |
| train on FlaMBe tool annotations instead of Softcite | PubMedBERT tool NER · FlaMBe held-out 11 papers | recall: 0.528 -> 0.909 | Improved |
| use PubMedBERT instead of BERT-base | tissue/cell type NER · FlaMBe abstracts cell type | F1: 0.779 -> 0.813 | Improved |
| use PubMedBERT instead of BERT-base | tissue/cell type NER · FlaMBe abstracts tissue | F1: 0.812 -> 0.856 | Improved |
| use BioELECTRA instead of ELECTRA | tissue NER · FlaMBe abstracts tissue | precision: 0.819 -> 0.751 | Hurt |
| use BioELECTRA instead of ELECTRA | tissue NER · FlaMBe abstracts tissue | recall: 0.841 -> 0.894 | Improved |
| use BioBERT instead of PubMedBERT | tissue NER · FlaMBe abstracts tissue | precision: 0.844 -> 0.848 | Improved |
| use BioELECTRA instead of ELECTRA | cell type NER · FlaMBe abstracts cell type | recall: 0.802 -> 0.855 | Improved |
| predict clustering context instead of alignment context | PubMedBERT one-vs-rest · tool context prediction | AUC: 0.954 -> 0.810 | Hurt |
Closest papers by meaning
- CellVerse: Do Large Language Models Really Understand Cell Biology? (NeurIPS 2025 · similarity 0.83)
- scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery (NeurIPS 2025 · similarity 0.83)
- Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data (NeurIPS 2024 · similarity 0.82)
- BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature (CVPR 2025 · similarity 0.82)
- Well-Written Knowledge Graphs: Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Texts (Student Abstract) (AAAI 2024 · similarity 0.82)
- Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs: Applying Large Language Models to Wikipedia and Linked Open Data (AAAI 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
